HuggingFaceH4
/

zephyr-7b-alpha

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Resources

View closed (11)

[AUTOMATED] Model Memory Requirements

#21 opened about 2 years ago by

model-sizer-bot

Potential Inconsistencies Model and Base Model License

#41 opened 5 months ago by

major problem couldnt find a fix

#40 opened 6 months ago by

Stopped to work

#39 opened over 1 year ago by

Am I the only one who gets the input also in the output of the API ? Is it possible to fix that? (example below)

#38 opened over 1 year ago by

Update README.md

#37 opened over 1 year ago by

Hugging Face's Zephyr Settings and System Prompt

#36 opened over 1 year ago by

ParanoidPosition

How to apply PEFT in this model

#35 opened almost 2 years ago by

Why the chosen rewards are negative?

#34 opened almost 2 years ago by

Incorrect Token Count in Generated Response

#33 opened almost 2 years ago by

Adding Evaluation Results

#32 opened almost 2 years ago by

leaderboard-pr-bot

Zephyr 7b 128k?

#31 opened almost 2 years ago by

High GPU RAM usage

#30 opened almost 2 years ago by

Is this model commercially usable?

#28 opened about 2 years ago by

ImportError

#26 opened about 2 years ago by

How can I teach another language by applying the Fine-tune process to this language model?

#25 opened about 2 years ago by

Train it with custom data

#24 opened about 2 years ago by

tokenization

#23 opened about 2 years ago by

Sample code not working

#22 opened about 2 years ago by

Hosted Inference API

#20 opened about 2 years ago by

Model answering with all newlines?

#19 opened about 2 years ago by

Is zephyr removed too?

#18 opened about 2 years ago by

Not working in Text Generation Web UI

#17 opened about 2 years ago by

Better or worse than Mistral?

#16 opened about 2 years ago by

Add pipeline_tag=conversational for Hosted inference API/demo to work

#15 opened about 2 years ago by

APIs & Fine-tuning ( both Domain Adaptation and instruction fine-tuning) on $/1000 token basis

#12 opened about 2 years ago by

KeyError: 'mistral'

#9 opened about 2 years ago by

Slow generation

#6 opened about 2 years ago by

Training/finetuning code?

#5 opened about 2 years ago by

Translation capability broken

#4 opened about 2 years ago by

Prompt format?

#3 opened about 2 years ago by